[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20110222111408.GH16508@amd.com>
Date: Tue, 22 Feb 2011 12:14:08 +0100
From: "Roedel, Joerg" <Joerg.Roedel@....com>
To: Avi Kivity <avi@...hat.com>, Marcelo Tosatti <mtosatti@...hat.com>
CC: "kvm@...r.kernel.org" <kvm@...r.kernel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
Zachary Amsden <zamsden@...hat.com>
Subject: Re: [PATCH 1/6] KVM: SVM: Advance instruction pointer in
dr_intercept
On Wed, Feb 09, 2011 at 12:29:39PM -0500, Joerg Roedel wrote:
> In the dr_intercept function a new cpu-feature called
> decode-assists is implemented and used when available. This
> code-path does not advance the guest-rip causing the guest
> to dead-loop over mov-dr instructions. This is fixed by this
> patch.
>
> Signed-off-by: Joerg Roedel <joerg.roedel@....com>
> ---
> arch/x86/kvm/svm.c | 2 ++
> 1 files changed, 2 insertions(+), 0 deletions(-)
>
> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
> index 73a8f1d..bfb4948 100644
> --- a/arch/x86/kvm/svm.c
> +++ b/arch/x86/kvm/svm.c
> @@ -2777,6 +2777,8 @@ static int dr_interception(struct vcpu_svm *svm)
> kvm_register_write(&svm->vcpu, reg, val);
> }
>
> + skip_emulated_instruction(&svm->vcpu);
> +
> return 1;
> }
Btw. Can you meanwhile apply this patch? It fixes a bug which sends the
guest into an endless loop when decode assists is available on the host.
Joerg
--
AMD Operating System Research Center
Advanced Micro Devices GmbH Einsteinring 24 85609 Dornach
General Managers: Alberto Bozzo, Andrew Bowd
Registration: Dornach, Landkr. Muenchen; Registerger. Muenchen, HRB Nr. 43632
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists